Ad Advance ced Deep Learn rning for r Comput uter r Vision - - PowerPoint PPT Presentation

▶
ad advance ced deep learn rning for r comput uter r vision
SMART_READER_LITE
LIVE PREVIEW

Ad Advance ced Deep Learn rning for r Comput uter r Vision - - PowerPoint PPT Presentation

Dec 16, 2022 489 likes •679 views

Ad Advance ced Deep Learn rning for r Comput uter r Vision Prof. Leal-Taix and Prof. Niessner 1 The Te The Team Lecturers Prof. Dr. Laura Prof. Dr. Matthias Leal-Taix Niessner Tutors Dave Ji Tim Maxim Chen Hou Meinhardt

slide-1
SLIDE 1
  • Prof. Leal-Taixé and Prof. Niessner

Ad Advance ced Deep Learn rning for r Comput uter r Vision

1

slide-2
SLIDE 2
  • Prof. Leal-Taixé and Prof. Niessner

Lecturers

  • Prof. Dr. Laura

Leal-Taixé

  • Prof. Dr. Matthias

Niessner Tim Meinhardt

Tutors

The The Te Team

2

Ji Hou Maxim Maximov Dave Chen

slide-3
SLIDE 3
  • Prof. Leal-Taixé and Prof. Niessner

Wh What at is this cou

  • urse

e ab abou

  • ut
  • Presentation of advanced Deep Learning methods for

various Computer Vision tasks

  • Focus on new methods, some of them presented
  • nly this year! There will be extra references, many
  • pportunities for you to dig deeper into the topics
  • Research-oriented course

3

slide-4
SLIDE 4
  • Prof. Leal-Taixé and Prof. Niessner

Wh While e we e go

  • ov
  • ver

er new ew met ethods

  • ds…
  • You have to come up with your own ideas to solve a

specific vision problem!

  • Strong focus on the practical side: semester-long

project where you can put all the knowledge to practice

4

slide-5
SLIDE 5
  • Prof. Leal-Taixé and Prof. Niessner

IM IMPORTANT

  • The project is VERY time-consuming, we are aware.
  • Since the project is done in teams of 2, we want to

avoid students dropping mid-semester!

  • Please think carefully whether you have the time this

semester to dedicate a lot of time to ADL4CV, if not, we kindly ask you to consider to take the course another semester.

5

slide-6
SLIDE 6
  • Prof. Leal-Taixé and Prof. Niessner

Course Course orga

  • rganizati

tion

  • n

6

slide-7
SLIDE 7
  • Prof. Leal-Taixé and Prof. Niessner

Ab About t the the lectu ture

  • Theory: 12 lectures
  • Every Monday 10

10:0 :00-11: 11:30 30h h & Friday 14 14:00-16 16:00h

  • Seminar Room, 02.13.010 online!
  • Practical:
  • Project to be done in groups of 2 (non-negotiable!)
  • Presentations during the semester (we will see how)
  • Final poster presentation

https://dvl.in.tum.de/teaching/adl4cv-ss20/

7

slide-8
SLIDE 8
  • Prof. Leal-Taixé and Prof. Niessner

Gra Grading syst g system

  • Exam: tbd

tbd

  • Review: 2 review sessions
  • Practical part = 2/3 of the grade
  • Exam = 1/3 of the grade

8

https://dvl.in.tum.de/teaching/adl4cv-ss20/

slide-9
SLIDE 9
  • Prof. Leal-Taixé and Prof. Niessner

Pr Project ct deadli line

  • 24.04., Friday: project presentation
  • 04.05.: project assignments (projects <-> TAs)
  • 11.

11.05., , midni night ht: deliver a a 1 1 pag age ab abstrac act of your idea a for the he project.

  • Until 15.05.: Evaluation of the project and feedback

9

slide-10
SLIDE 10
  • Prof. Leal-Taixé and Prof. Niessner

Pr Project ct evalu luation

  • Presentations: everyone needs to attend!
  • First present

ntat ation: n: first results, , chal halleng nges

– 08 08.06 06: : Groups #1 – 12 12.06: : Groups #2

10

slide-11
SLIDE 11
  • Prof. Leal-Taixé and Prof. Niessner

Pr Project ct evalu luation

  • Presentations: everyone needs to attend!
  • Second

nd present ntat ation: n: al almost final nal results, , ne new w thi hing ngs yo you tried

– 06. 6.07.: : Groups #1 – 10 10.07: : Groups #2

11

slide-12
SLIDE 12
  • Prof. Leal-Taixé and Prof. Niessner

Pr Project ct evalu luation

  • Presentations: everyone needs to attend!
  • 20.07.

7.: final nal dead adline ne on n report (dead adline ne no noon) n) – Max 4 pages using CVPR template

  • Final

nal present ntat ation n = POS POSTER ER – Date 24.07. 14:00-16:00

12

slide-13
SLIDE 13
  • Prof. Leal-Taixé and Prof. Niessner

Gra Grading syst g system

  • Exam = 1/3 of the grade
  • Practical part = 2/3 of the grade

– Presentations (2 oral pres. + 1 poster) = 1/3 – Final report = 1/3 – Code/submission = 1/3

13

slide-14
SLIDE 14
  • Prof. Leal-Taixé and Prof. Niessner

Fo Followin ing u up w wit ith t the p projects

  • Each project will be assigned to a TA and you will

have weekly office hours to discuss the progress

  • These will be announced after the projects are

approved

14

slide-15
SLIDE 15
  • Prof. Leal-Taixé and Prof. Niessner

Sli Slides

  • Moodle is set up! Lecture will be entirely online.
  • Slides will be posted on Moodle and on the website:

https://dvl.in.tum.de/teaching/adl4cv-ss20/

  • Questions regarding organization of the course:
  • Emails to our individual addresses will not be answered!

adl4cv@dvl.in.tum.de

15

slide-16
SLIDE 16
  • Prof. Leal-Taixé and Prof. Niessner

Te Teams

  • Teams of two per project!
  • Moodle is set up!
  • If you do not have a team

– Chat after the lecture – Post it on Moodle

16

slide-17
SLIDE 17

Pr Project ct Timeli line

  • April 24th Project proposal presentations
  • May 4th Projects Assignments (and TA assignments)
  • May 11th Abstract Submissions (midnight)
  • Until May 15th -> Feedback Projects
  • 8th + 12th June -> First presentations (group #1, #2)
  • 6th + 10th July -> Second presentation (group #1, #2)
  • July 20th -> Deadline report (noon)
  • July 24th -> Poster Presentation (14-16h)

51

slide-18
SLIDE 18
  • Prof. Leal-Taixé and Prof. Niessner

Ad Advance ced Deep Learn rning for r Comput uter r Vision

52